CN110695562A - Welding quality online detection system and method - Google Patents
Welding quality online detection system and method Download PDFInfo
- Publication number
- CN110695562A CN110695562A CN201910915608.XA CN201910915608A CN110695562A CN 110695562 A CN110695562 A CN 110695562A CN 201910915608 A CN201910915608 A CN 201910915608A CN 110695562 A CN110695562 A CN 110695562A
- Authority
- CN
- China
- Prior art keywords
- welding
- upper computer
- weldment
- detected
- guide rail
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/12—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to investigating the properties, e.g. the weldability, of materials
- B23K31/125—Weld quality monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Mechanical Engineering (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention provides an online detection system for welding quality, which comprises a line structure light sensing module, an acoustic signal acquisition module, a support, a guide rail, a driving mechanism, an upper computer and a display module, wherein the support is arranged beside a weldment to be detected, the guide rail is arranged above the weldment to be detected, and two ends of the guide rail are respectively supported on the support; the line structure light sensing module and the acoustic signal acquisition module are arranged in the mounting frame, the mounting frame is connected with the guide rail, and the driving mechanism drives the guide rail to move; the line structure light sensing module and the acoustic signal acquisition module are respectively connected with an upper computer, a first output end of the upper computer is connected with an input end of the driving mechanism, and a second output end of the upper computer is connected with an input end of the display module. The invention also provides an online welding quality detection method, which is applied to the online welding quality detection system. The invention can effectively overcome the defect that auxiliary detection materials or detection processes in the prior art have different degrees of harm to human bodies.
Description
Technical Field
The invention relates to the technical field of welding equipment, in particular to an online welding quality detection system and an online welding quality detection method.
Background
During the welding process, the welding quality problem is often accompanied in the welding seam due to welding materials, process deviation, welding environment and the like. The welding defects mainly include the following two types: one type is the weld surface external defects which can be seen by naked eyes or a low power magnifier, such as undercut, welding beading, craters, surface pores, slag inclusions, surface cracks, unreasonable weld positions and the like; another type is internal defects that must be detected by destructive testing or special non-destructive inspection methods, such as internal porosity, slag inclusions, internal cracks, lack of penetration, lack of fusion, etc. The quality of welding has a serious impact on the development of industry and the safety of users, even disastrous accidents are caused.
The conventional welding defect nondestructive detection method comprises the following steps: radiography, ultrasonography, penetrant testing, magnetic particle testing, eddy current testing, and the like. However, the existing nondestructive detection method for welding defects still has defects of different degrees, for example, the detection rate of the radiographic method for crack defects is influenced by the transillumination angle, the thin layer defects in the vertical irradiation direction cannot be detected, and the rays in the detection process are harmful to human bodies and need to take protective measures; the penetration detection can only detect the surface opening defect of the material, the components of the penetrating agent have certain corrosivity on the detected workpiece, and the organic solvent used by the penetrating agent has volatility and has certain harm to a human body.
Disclosure of Invention
The invention provides an on-line welding quality detection system and method for overcoming the defect that auxiliary detection materials or detection processes in the prior art have different degrees of harm to human bodies.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a welding quality online detection system comprises a linear structure light sensing module, an acoustic signal acquisition module, a support, a guide rail, a driving mechanism, an upper computer and a display module, wherein the support is arranged beside a weldment to be detected, the guide rail is arranged above the weldment to be detected, and two ends of the guide rail are respectively supported on the support; the line structure light sensing module and the acoustic signal acquisition module are arranged in the mounting frame, the mounting frame is connected with the guide rail, and the driving mechanism drives the guide rail to move; the line structure light sensing module and the acoustic signal acquisition module are respectively connected with an upper computer, a first output end of the upper computer is connected with an input end of the driving mechanism, and a second output end of the upper computer is connected with an input end of the display module.
In the using process, the bracket is arranged above the weldment to be welded, and the guide rail is supported on the bracket and is arranged right above the weldment to be welded. In the welding process of the weldment, the upper computer sends a driving signal to the driving mechanism, the driving mechanism controls the guide rail to move according to the received driving signal, the mounting frame is made to move to a target starting position and move at the same speed as the welding gun, the sound signal acquisition module on the mounting frame works and acquires welding sound signals of the weldment to be detected, and then the welding sound signals are transmitted to the upper computer to be subjected to waveform processing, so that the welding defect type is obtained. After the weldment is welded, the upper computer sends a driving signal to the driving mechanism again, the driving mechanism controls the guide rail to move at the same speed, the mounting frame moves above the weldment to be detected at the same speed, the linear structure light sensing module collects linear spot images on the welding seam of the weldment to be detected and transmits the linear spot images to the upper computer for image processing, the outline image of the welding seam is obtained, and finally the upper computer transmits a data processing result to the display module for real-time display.
In the technical scheme, the line-structured light sensing module is used for projecting a laser signal to the surface of a weldment to be detected and acquiring an image, and then calculating the position and depth information of a welding line according to the change of the light signal caused by the welding line on the weldment to be detected; the acoustic signal acquisition module is used for acquiring acoustic signals in the welding process, wherein the acoustic signals comprise welding acoustic signals caused by pressure stirring of plasma sprayed from a small hole in a small hole mode in the laser welding process, or welding acoustic signals generated by continuous impact of a molten pool and high-frequency oscillation of the inside of an electric arc in the electric arc welding process, and internal acoustic signals which are caused by redistribution of materials due to change of the internal structure of the materials and are converted from mechanical energy to acoustic energy, and the upper computer can perform waveform processing according to the acquired acoustic signals to obtain the welding defect type of the weldment to be detected; the driving mechanism is used for controlling the guide rail to move according to a driving signal sent by the upper computer, so that the mounting rack which is connected with the guide rail and is provided with the linear structure light sensing module and the acoustic signal acquisition module moves along the guide rail; the display module is used for detecting the welding quality detection result of the weldment to be detected in real time.
Preferably, the line structured light sensing module comprises a laser and an image acquisition unit, wherein the laser projects light to the weldment to be detected according to a working signal output by the upper computer, and the image acquisition unit acquires an optical signal reflected by the weldment to be detected according to the working signal output by the upper computer.
Preferably, the mounting bracket is the box structure, and the box downside has seted up the observation frame, and the laser instrument is through observing the frame to waiting to detect weldment transmission laser, and the image acquisition unit is through observing the frame and gathering the laser signal who detects weldment reflection.
Preferably, the sound signal acquisition module comprises a sound sensor, a data acquisition unit and an AD converter, wherein the output end of the sound sensor is connected with the input end of the data acquisition unit, the output end of the data acquisition unit is connected with the input end of the AD converter, and the output end of the AD converter is connected with the input end of the upper computer.
Preferably, the mounting bracket downside has been seted up the vacancy, and sound sensor's collection end process the vacancy is worn out the mounting bracket setting.
Preferably, the collection end of the sound sensor is arranged at a position 10-15 cm above the weldment to be detected, and the image collection unit is arranged at a position 30-40 cm above the weldment to be detected. .
Preferably, the guide rail comprises a transverse guide rail and a longitudinal guide rail, and the mounting rack is connected with the longitudinal guide rail in a sliding manner; the back side of the longitudinal rail is slidably connected with the transverse rail.
The invention also provides a welding quality online detection method, which is applied to the welding quality online detection system and comprises the following steps:
s1: placing the weldment to be detected on a workbench, sending a driving signal to a driving mechanism by an upper computer, and controlling the guide rail to move by the driving mechanism so as to enable the mounting rack to move to a target position;
s2: the welding gun welds the weldment to be detected, meanwhile, the upper computer sends a driving signal to the driving mechanism, the driving mechanism controls the guide rail to move at the same speed as the welding gun according to the received driving signal, the sound signal acquisition module on the mounting frame works and acquires a welding sound signal of the weldment to be detected, and then the welding sound signal is transmitted to the upper computer for waveform processing to obtain the type of welding defects;
s3: after the weldment to be detected is welded, the upper computer sends a driving signal to the driving mechanism again, the driving mechanism controls the guide rail to move at the same speed, and the linear structure light sensing module collects linear spot images on the welding seam of the weldment to be detected and transmits the linear spot images to the upper computer for image processing to obtain a contour image of the welding seam;
s4: and the upper computer establishes a three-dimensional model according to the data processing result to feed back the welding quality, and transmits the real appearance profile image of the welding seam, the welding defect type and the three-dimensional model image of the welding seam to a display module for real-time display.
Preferably, the data processing process of the line structured light sensing module and the acoustic signal acquisition module includes the following specific steps:
the line structure light sensing module collects a line spot image of a laser device on a welding seam of a weldment to be detected and transmits the line spot image to the upper computer through the image collecting unit, the upper computer extracts a target contour through a line spot of the laser device on the welding seam, and a real appearance contour of the welding seam is obtained by combining a camera calibration result;
the upper computer analyzes the welding sound signals in time domain, frequency domain and time-frequency domain to extract characteristic parameters, establishes mapping relations between different welding defect states and the welding sound signals, establishes a welding defect identification and classification model, and obtains the welding defect type through the welding defect identification and classification model according to the welding sound signals acquired in real time.
Preferably, the model for identifying and classifying the welding defects comprises an artificial intelligence model supporting one or more of a vector machine, Mel frequency cepstral coefficients, and sound identification in an RNN neural network.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that: welding quality detection is carried out on the welding piece by combining the linear structure optical sensing module and the acoustic signal acquisition module, so that the analysis of weld surface defects and the identification and classification of weld internal defects are realized, and the requirements of real-time performance and accuracy of the welding quality detection are met; auxiliary detection materials are not needed, and harm of the auxiliary detection materials or the detection process to human bodies in different degrees is effectively avoided.
Drawings
Fig. 1 is a schematic structural view of an on-line welding quality detection system according to embodiment 1.
Fig. 2 is a schematic structural diagram of a line structured light sensing module in embodiment 1.
Fig. 3 is a schematic structural view of the mount of embodiment 1.
Fig. 4 is a flowchart of the welding quality on-line detection method of embodiment 2.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
Fig. 1 is a schematic structural diagram of the welding quality on-line detection system of the present embodiment.
The embodiment provides an online detection system for welding quality, which comprises a line-structured light sensing module 1, an acoustic signal acquisition module 2, a support 3, a guide rail 4, a driving mechanism, an upper computer 5 and a display module 6, wherein the support 3 is arranged above a weldment to be detected, and two ends of the guide rail 4 are respectively supported on the support 3; the line-structured light sensing module 1 and the acoustic signal acquisition module 2 are arranged in the mounting rack 7, the mounting rack 7 is connected with the guide rail 4, and the driving mechanism drives the guide rail 4 to move; line structure light sensing module 1, acoustic signal collection module 2 are connected with upper computer 5 respectively, and the first output of upper computer 5 is connected with actuating mechanism's input, and the second output of upper computer 5 is connected with display module 6's input.
In this embodiment, the line structured light sensing module 1 includes a laser 11 and an image collecting unit 12, wherein the laser 11 projects light to the weldment to be detected according to the working signal output by the upper computer 5, and the image collecting unit 12 collects the light signal reflected by the weldment to be detected according to the working signal output by the upper computer 5. The acoustic signal acquisition module 2 comprises an acoustic sensor 21, a data acquisition unit and an AD converter, wherein the output end of the acoustic sensor 21 is connected with the input end of the data acquisition unit, the output end of the data acquisition unit is connected with the input end of the AD converter, and the output end of the AD converter is connected with the input end of the upper computer 5. Fig. 2 is a schematic structural diagram of the line structured light sensing module of the present embodiment.
In the embodiment, the mounting frame 7 is of a box structure, an observation frame 71 is arranged on the lower side surface of the box, the laser 11 emits laser to the weldment to be detected through the observation frame 71, and the image acquisition unit 12 acquires a laser signal reflected by the weldment to be detected through the observation frame 71; the box downside has still seted up the hole 72, and the sound sensor 21 in the acoustic signal collection module 2 stretches out the mounting bracket setting through hole 72, the collection of the acoustic sensor 21 of being convenient for to the acoustic signal. Fig. 3 is a schematic structural diagram of the mounting bracket 7 of the present embodiment.
In this embodiment, the guide rail 4 includes a transverse guide rail 41 and a longitudinal guide rail 42, and the mounting bracket 7 is slidably connected to the longitudinal guide rail 42; the back side of the longitudinal rail 42 is slidably connected to the transverse rail 41.
In the embodiment, the image acquisition unit 1 is arranged at a position 30-40 cm above the weldment to be detected, and the acquisition end of the sound sensor 21 is arranged at a position 10-15 cm above the weldment to be detected.
In the present embodiment, a camera is used as the image pickup unit 12, a microphone is used as the sound sensor 21, and a liquid crystal display is used as the display module 6.
In the specific implementation process, a weldment to be detected is placed on the workbench, the bracket 3 is arranged above the weldment to be detected, and the guide rail 4 is supported on the bracket 3 and is arranged right above the weldment to be detected. Then, a working signal is sent to the driving mechanism through the upper computer 5, and the driving mechanism controls the movement of the transverse guide rail 41 and the longitudinal guide rail 42 according to the received driving signal, so that the linear structure light sensing module 1 and the acoustic signal acquisition module 2 move to the target initial position.
When a weldment to be detected starts to be welded, the driving mechanism controls the transverse guide rail 41 to move at the same moving speed as that of a welding gun, the upper computer 5 sends a working signal to the acoustic signal acquisition module 2, the acoustic signal acquisition module 2 works, and the sound sensor 21 acquires an acoustic signal. Wherein the collected acoustic signals comprise welding acoustic signals caused by pressure stirring of plasma jetted from the small hole in a small hole mode in the laser welding process, or welding acoustic signals generated by continuous impact of a molten pool and self high-frequency oscillation in the electric arc welding process, and internal acoustic signals caused by material redistribution due to change of the internal structure of the material. The sound sensor 21 sends the collected sound signals to the upper computer 5 for waveform processing after the sound signals are processed by the data collector and the AD converter. Specifically, the upper computer 5 performs time domain, frequency domain and time-frequency domain waveform analysis on a large amount of collected acoustic signal data by adopting fourier transform, wavelet transform and S transform, constructs a welding defect identification and classification model by combining with the RNN neural network, and inputs the acoustic signal collected in the detection process into the welding defect identification and classification model to obtain the type of the welding defect.
When the weldment to be detected is welded and the weld joint is cooled and formed, the upper computer 5 sends a driving signal to the driving mechanism to control the transverse guide rail 41 to move, so that the mounting frame 7 returns to the target starting position and moves along the transverse guide rail at the same speed, and the linear structure light sensing module 1 finishes scanning the weld joint at the same working speed as the acoustic signal acquisition module 2. Specifically, light emitted by the laser 11 is irradiated on a welding seam of a weldment to be detected, the image acquisition unit 12 acquires a speckle image on the welding seam and transmits the speckle image to the upper computer 5, and the upper computer 5 obtains a real appearance profile of the welding seam by combining with a camera calibration result. The upper computer 5 reconstructs a three-dimensional model of the welding seam through a three-dimensional reconstruction algorithm according to the type of the welding defect and the real appearance contour of the welding seam to obtain a three-dimensional model image of a welding quality detection result, and finally transmits the linear structure light image information, the welding seam three-dimensional model image, the acoustic signal waveform image, the welding state parameter information and the welding defect feedback graph information based on the three-dimensional model to the display module 6 for real-time display.
In this embodiment, the line structured light sensing module 1 calculates the weld state parameter information such as the position and depth of the object according to the change of the light signal caused by the object, so as to reveal the morphological characteristics of the weld surface and characterize the defect types of the weld surface, such as undercut, flash, crater, surface air hole, slag inclusion, surface crack, unreasonable weld position, and the like; the signals acquired by the acoustic signal acquisition module 2 are subjected to real-time feedback of the quality state of the welding seam through a pre-trained welding seam defect identification model based on the welding acoustic signals, and the defect states inside the welding seam, such as internal pores, slag inclusions, internal cracks, incomplete penetration, incomplete fusion and the like, can be known through identification and classification. The welding quality on-line detection system provided by the embodiment detects the welding quality of the welding piece by combining the linear structured light sensing module 1 and the acoustic signal acquisition module 2, realizes the analysis of the surface defects of the welding seam and the identification and classification of the internal defects of the welding seam, meets the requirements of real-time performance and accuracy of welding quality detection, and effectively solves the defect that the auxiliary detection material or the detection process has different degrees of harm to the human body in the prior art.
Example 2
The embodiment provides an online welding quality detection method, which is applied to the online welding quality detection system provided in embodiment 1. Fig. 4 is a flowchart of the welding quality on-line detection method of the present embodiment.
The welding quality online detection method of the embodiment comprises the following steps:
s1: the weldment to be detected is placed on the workbench, the upper computer 5 sends a driving signal to the driving mechanism, and the driving mechanism controls the guide rail 4 to move so that the mounting frame 7 moves to a target position.
S2: the welding gun welds the weldment to be detected, meanwhile, the upper computer 5 sends a driving signal to the driving mechanism, the driving mechanism controls the guide rail to move at the same speed as the welding gun according to the received driving signal, wherein the sound signal acquisition module 2 on the mounting frame 7 works and acquires a welding sound signal of the weldment to be detected, and then the welding sound signal is transmitted to the upper computer 5 for waveform processing to obtain the type of welding defects;
in this step, the sound sensor 21 in the sound signal collection module 2 collects a large amount of welding sound signals and transmits the welding sound signals to the upper computer 5 through the data collector, the upper computer 5 extracts characteristic parameters of the welding sound signals through waveform analysis of time domain, frequency domain and time-frequency domain, establishes mapping relations between different welding defect states and the welding sound signals, establishes a model for identifying and classifying the welding defects, and then obtains the types of the welding defects through the model for identifying and classifying the welding defects.
In the embodiment, a model for identifying and classifying the welding defects is constructed through sound identification models such as a vector machine, mel frequency cepstrum coefficients and an RNN neural network.
S3: after the weldment to be detected is welded, the upper computer 5 sends a driving signal to the driving mechanism again, the driving mechanism controls the guide rail 4 to move at the same speed, and the linear structure light sensing module 1 collects linear spot images on the welding seam of the weldment to be detected and transmits the linear spot images to the upper computer 5 for image processing to obtain a contour image of the welding seam.
In this step, the image acquisition unit 12 in the line structured light sensing module 1 acquires a spot image of the laser 11 on the weld of the weldment to be detected, and transmits the spot image to the upper computer 5, and the upper computer 5 extracts a target profile through the acquired spot image, and then obtains a real morphology profile image of the weld by combining a camera calibration result.
S4: and the upper computer 5 establishes a three-dimensional model to feed back the welding quality according to the image processing result and the waveform processing result, and transmits the real appearance profile image of the welding seam, the welding defect type and the three-dimensional model image of the welding seam to a display module 6 for real-time display.
In the embodiment, LabVIEW graphical programming software is adopted to construct the weld three-dimensional model image.
In the specific implementation process, a weldment to be detected is placed on the workbench, the bracket 3 is arranged above the weldment to be detected, and the guide rail 4 is supported on the bracket 3 and is arranged right above the weldment to be detected. Then, a working signal is sent to the driving mechanism through the upper computer 5, and the driving mechanism controls the movement of the transverse guide rail 41 and the longitudinal guide rail 42 according to the received driving signal, so that the linear structure light sensing module 1 and the acoustic signal acquisition module 2 move to the target initial position.
When a weldment to be detected starts to be welded, the driving mechanism controls the transverse guide rail 41 to move at the same moving speed as that of a welding gun, the upper computer 5 sends a working signal to the acoustic signal acquisition module 2, the acoustic signal acquisition module 2 works, and the sound sensor 21 acquires an acoustic signal. Wherein the collected acoustic signals comprise welding acoustic signals caused by pressure stirring of plasma jetted from the small hole in a small hole mode in the laser welding process, or welding acoustic signals generated by continuous impact of a molten pool and self high-frequency oscillation in the electric arc welding process, and internal acoustic signals caused by material redistribution due to change of the internal structure of the material. The sound sensor 21 sends the collected sound signals to the upper computer 5 for waveform processing after the sound signals are processed by the data collector and the AD converter. Specifically, the upper computer 5 performs time domain, frequency domain and time-frequency domain waveform analysis on a large amount of collected acoustic signal data by adopting fourier transform, wavelet transform and S transform, constructs a welding defect identification and classification model by combining with the RNN neural network, and inputs the acoustic signal collected in the detection process into the welding defect identification and classification model to obtain the type of the welding defect.
When the weldment to be detected is welded and the weld joint is cooled and formed, the upper computer 5 sends a driving signal to the driving mechanism to control the transverse guide rail 41 to move, so that the mounting frame 7 returns to the target starting position and moves along the transverse guide rail at the same speed, and the linear structure light sensing module 1 finishes scanning the weld joint at the same working speed as the acoustic signal acquisition module 2. Specifically, light emitted by the laser 11 is irradiated on a welding seam of a weldment to be detected, the image acquisition unit 12 acquires a speckle image on the welding seam and transmits the speckle image to the upper computer 5, and the upper computer 5 obtains a real appearance profile of the welding seam by combining with a camera calibration result. The upper computer 5 reconstructs a three-dimensional model of the welding seam through a three-dimensional reconstruction algorithm according to the type of the welding defect and the real appearance contour of the welding seam to obtain a three-dimensional model image of a welding quality detection result, and finally transmits the linear structure light image information, the welding seam three-dimensional model image, the acoustic signal waveform image, the welding state parameter information and the welding defect feedback graph information based on the three-dimensional model to the display module 6 for real-time display.
The same or similar reference numerals correspond to the same or similar parts;
the terms describing positional relationships in the drawings are for illustrative purposes only and are not to be construed as limiting the patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. The welding quality online detection system is characterized by comprising a line structure light sensing module, an acoustic signal acquisition module, a support, a guide rail, a driving mechanism, an upper computer and a display module, wherein the support is arranged beside a weldment to be detected, the guide rail is arranged above the weldment to be detected, and two ends of the guide rail are respectively supported on the support; the line structure light sensing module and the acoustic signal acquisition module are arranged in the mounting frame, the mounting frame is connected with the guide rail, and the driving mechanism drives the guide rail to move; the line structure light sensing module and the acoustic signal acquisition module are respectively connected with an upper computer, a first output end of the upper computer is connected with an input end of the driving mechanism, and a second output end of the upper computer is connected with an input end of the display module.
2. The welding quality on-line detection system of claim 1, wherein: the line structure light sensing module comprises a laser and an image acquisition unit, the laser projects light to the weldment to be detected according to a working signal output by the upper computer, and the image acquisition unit acquires an optical signal reflected by the weldment to be detected according to the working signal output by the upper computer.
3. The welding quality on-line detection system of claim 2, wherein: the mounting bracket is the box structure, the observation frame has been seted up to the box downside, the laser instrument process the observation frame is to waiting to detect weldment transmission laser, the image acquisition unit process the observation frame gathers and waits to detect the laser signal of weldment reflection.
4. The welding quality on-line detection system of claim 3, wherein: the acoustic signal collection module comprises an acoustic sensor, a data acquisition unit and an AD converter, wherein the output end of the acoustic sensor is connected with the input end of the data acquisition unit, the output end of the data acquisition unit is connected with the input end of the AD converter, and the output end of the AD converter is connected with the input end of the upper computer.
5. The welding quality on-line detection system of claim 4, wherein: the mounting bracket downside has been seted up the vacancy, sound sensor's collection end process the mounting bracket setting is worn out to the vacancy.
6. The welding quality online detection system according to any one of claims 1 to 5, characterized in that: the guide rail includes transverse guide and longitudinal rail, mounting bracket and longitudinal rail sliding connection, the dorsal part and the transverse guide sliding connection of longitudinal rail.
7. The welding quality on-line detection system of claim 6, wherein: the collection end of the sound sensor is arranged at a position 10-15 cm above the weldment to be detected, and the image collection unit is arranged at a position 30-40 cm above the weldment to be detected.
8. The welding quality online detection method is characterized by comprising the following steps:
s1: placing the weldment to be detected on a workbench, sending a driving signal to a driving mechanism by an upper computer, and controlling the guide rail to move by the driving mechanism so as to enable the mounting rack to move to a target position;
s2: the welding gun welds the weldment to be detected, meanwhile, the upper computer sends a driving signal to the driving mechanism, the driving mechanism controls the guide rail to move at the same speed as the welding gun according to the received driving signal, the sound signal acquisition module on the mounting frame works and acquires a welding sound signal of the weldment to be detected, and then the welding sound signal is transmitted to the upper computer for waveform processing to obtain the type of welding defects;
s3: after the weldment to be detected is welded, the upper computer sends a driving signal to the driving mechanism again, the driving mechanism controls the guide rail to move at the same speed, and the linear structure light sensing module collects linear spot images on the welding seam of the weldment to be detected and transmits the linear spot images to the upper computer for image processing to obtain a contour image of the welding seam;
s4: and the upper computer establishes a three-dimensional model according to the data processing result to feed back the welding quality, and transmits the real appearance profile image of the welding seam, the welding defect type and the three-dimensional model image of the welding seam to a display module for real-time display.
9. The welding quality on-line detection method according to claim 8, characterized in that: in the data processing process of the line structure light sensing module and the acoustic signal acquisition module, the method comprises the following specific steps:
the line structure light sensing module collects a line spot image of a laser device on a welding seam of a weldment to be detected and transmits the line spot image to the upper computer through the image collecting unit, the upper computer extracts a target contour through a line spot of the laser device on the welding seam, and a real appearance contour of the welding seam is obtained by combining a camera calibration result;
the acoustic signal acquisition module acquires a large number of welding acoustic signals and transmits the welding acoustic signals to the upper computer through the data acquisition unit, the upper computer analyzes the waveforms of the welding acoustic signals in a time domain, a frequency domain and a time-frequency domain to extract characteristic parameters, a mapping relation between different welding defect states and the welding acoustic signals is established, a welding defect identification and classification model is established, and then the welding acoustic signals acquired in real time pass through the welding defect identification and classification model to obtain the type of the welding defects.
10. The welding quality on-line monitoring method according to claim 8, characterized in that: the model for identifying and classifying the welding defects comprises one or more artificial intelligence models for sound identification in a support vector machine, a Mel frequency cepstrum coefficient and an RNN neural network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910915608.XA CN110695562A (en) | 2019-09-26 | 2019-09-26 | Welding quality online detection system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910915608.XA CN110695562A (en) | 2019-09-26 | 2019-09-26 | Welding quality online detection system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110695562A true CN110695562A (en) | 2020-01-17 |
Family
ID=69198018
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910915608.XA Pending CN110695562A (en) | 2019-09-26 | 2019-09-26 | Welding quality online detection system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110695562A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111650211A (en) * | 2020-06-23 | 2020-09-11 | 四川长虹电器股份有限公司 | Outer quick-witted base welding defect detecting system of air conditioner |
CN112666248A (en) * | 2020-12-16 | 2021-04-16 | 上海交通大学 | Weld defect automatic detection method and system based on deep learning |
CN112676676A (en) * | 2020-12-16 | 2021-04-20 | 武汉逸飞激光股份有限公司 | Tab welding method |
CN112756840A (en) * | 2021-01-25 | 2021-05-07 | 陕西帕源路桥建设有限公司 | Welding quality detection system |
CN112762852A (en) * | 2020-12-28 | 2021-05-07 | 广东工业大学 | Floating state manufacturing process deformation detection device and installation and detection method thereof |
CN112872631A (en) * | 2020-12-02 | 2021-06-01 | 深圳市裕展精密科技有限公司 | Welding detection method, welding detection device and computer-readable storage medium |
CN113029933A (en) * | 2021-02-26 | 2021-06-25 | 广东利元亨智能装备股份有限公司 | Welding quality detection system, ultrasonic welding equipment and welding quality detection method |
CN113049678A (en) * | 2021-03-22 | 2021-06-29 | 沈阳大学 | Weldment detection device and method based on sound field regulation and control |
CN113076817A (en) * | 2021-03-17 | 2021-07-06 | 上海展湾信息科技有限公司 | Weld pore defect real-time detection method and system |
CN113298806A (en) * | 2021-06-18 | 2021-08-24 | 上海市机械施工集团有限公司 | Intelligent detection method and device for welding defects, welding equipment and storage medium |
CN114101963A (en) * | 2021-12-14 | 2022-03-01 | 吉林大学 | Real-time evaluation method and device for flash butt welding quality of automobile rim |
CN114714022A (en) * | 2022-04-26 | 2022-07-08 | 唐山松下产业机器有限公司 | Welding quality detection method and device |
CN115980092A (en) * | 2023-03-20 | 2023-04-18 | 宁波吉宁汽车零部件有限公司 | Weld piece check out test set |
US20230166361A1 (en) * | 2021-11-30 | 2023-06-01 | GM Global Technology Operations LLC | Method and system for weld defect detection |
CN116754781A (en) * | 2023-08-18 | 2023-09-15 | 北京大学 | X-ray welding seam detection device based on automation and CR technology |
CN117066690A (en) * | 2023-09-28 | 2023-11-17 | 苏师大半导体材料与设备研究院(邳州)有限公司 | Alignment welding device for semiconductor processing |
-
2019
- 2019-09-26 CN CN201910915608.XA patent/CN110695562A/en active Pending
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111650211A (en) * | 2020-06-23 | 2020-09-11 | 四川长虹电器股份有限公司 | Outer quick-witted base welding defect detecting system of air conditioner |
CN112872631A (en) * | 2020-12-02 | 2021-06-01 | 深圳市裕展精密科技有限公司 | Welding detection method, welding detection device and computer-readable storage medium |
CN112666248A (en) * | 2020-12-16 | 2021-04-16 | 上海交通大学 | Weld defect automatic detection method and system based on deep learning |
CN112676676A (en) * | 2020-12-16 | 2021-04-20 | 武汉逸飞激光股份有限公司 | Tab welding method |
CN112762852A (en) * | 2020-12-28 | 2021-05-07 | 广东工业大学 | Floating state manufacturing process deformation detection device and installation and detection method thereof |
CN112756840A (en) * | 2021-01-25 | 2021-05-07 | 陕西帕源路桥建设有限公司 | Welding quality detection system |
CN113029933B (en) * | 2021-02-26 | 2021-11-16 | 广东利元亨智能装备股份有限公司 | Welding quality detection system, ultrasonic welding equipment and welding quality detection method |
CN113029933A (en) * | 2021-02-26 | 2021-06-25 | 广东利元亨智能装备股份有限公司 | Welding quality detection system, ultrasonic welding equipment and welding quality detection method |
CN113076817A (en) * | 2021-03-17 | 2021-07-06 | 上海展湾信息科技有限公司 | Weld pore defect real-time detection method and system |
CN113049678A (en) * | 2021-03-22 | 2021-06-29 | 沈阳大学 | Weldment detection device and method based on sound field regulation and control |
CN113298806A (en) * | 2021-06-18 | 2021-08-24 | 上海市机械施工集团有限公司 | Intelligent detection method and device for welding defects, welding equipment and storage medium |
US11839935B2 (en) * | 2021-11-30 | 2023-12-12 | GM Global Technology Operations LLC | Method and system for weld defect detection |
US20230166361A1 (en) * | 2021-11-30 | 2023-06-01 | GM Global Technology Operations LLC | Method and system for weld defect detection |
CN114101963A (en) * | 2021-12-14 | 2022-03-01 | 吉林大学 | Real-time evaluation method and device for flash butt welding quality of automobile rim |
CN114714022A (en) * | 2022-04-26 | 2022-07-08 | 唐山松下产业机器有限公司 | Welding quality detection method and device |
CN115980092A (en) * | 2023-03-20 | 2023-04-18 | 宁波吉宁汽车零部件有限公司 | Weld piece check out test set |
CN116754781B (en) * | 2023-08-18 | 2023-10-20 | 北京大学 | X-ray welding seam detection device based on automation and CR technology |
CN116754781A (en) * | 2023-08-18 | 2023-09-15 | 北京大学 | X-ray welding seam detection device based on automation and CR technology |
CN117066690A (en) * | 2023-09-28 | 2023-11-17 | 苏师大半导体材料与设备研究院(邳州)有限公司 | Alignment welding device for semiconductor processing |
CN117066690B (en) * | 2023-09-28 | 2024-01-23 | 苏师大半导体材料与设备研究院(邳州)有限公司 | Alignment welding device for semiconductor processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110695562A (en) | Welding quality online detection system and method | |
CN211122688U (en) | Welding quality on-line measuring system | |
EP3287778B1 (en) | System and method for nondestructive evaluation of a test object using acoustic thermography | |
CN207351966U (en) | The automatic ultrasonic detection device and system of sheet metal | |
CN107478722A (en) | A kind of new resonance acoustics the cannot-harm-detection device | |
CN205374371U (en) | Magneto -optic formation of image nondestructive test platform | |
CN116000453B (en) | Laser welding quality real-time monitoring method and system | |
KR101281582B1 (en) | Noncontact imaging method for nondestructive testing | |
CN115582559A (en) | Online monitoring system and online monitoring method for powder-laying additive manufacturing defects | |
EP4337948A1 (en) | Portable ultrasonic probe for polar scanning | |
Vasilev et al. | Non-contact in-process ultrasonic screening of thin fusion welded joints | |
CN115889975A (en) | Laser welding process monitoring system and method | |
WO2009007817A2 (en) | Method and apparatus for the contactless dynamic inspection of railway rails | |
ATE314900T1 (en) | DEVICE AND METHOD FOR MONITORING LASER WELDING AND GIVING A WELDING QUALITY STATEMENT | |
KR101444078B1 (en) | Nondestructive Testing Apparatus and Method for Penetration Nozzle of Control Rod Drive Mechanism of Reactor Vessel Head | |
CN112834616A (en) | Welding seam detection device and method | |
Maev | Acoustic microscopy for materials characterization | |
JP2007047116A (en) | Ultrasonic flaw detection method | |
CN116380890A (en) | Vehicle body welding spot detection method based on vision and ultrasonic detection | |
KR20220037769A (en) | Welding apparatus with ultrasonic inspection function | |
KR20070005767A (en) | Laser using welding flaw detecting for spiral welding pipe | |
CN208795700U (en) | A kind of composite weld ultrasonic wave adjustment test block | |
CN207571073U (en) | Aluminium alloy cast ingot defect-detecting equipment | |
Bastuck et al. | Acoustic in-process monitoring of laser welding | |
KR200383966Y1 (en) | Non-destructive tester using ultrasonic |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |